Research/Academic
PhD in artificial intelligence, with research on neuro-symbolic architectures for natural language comprehension applied across energy, healthcare and finance.
- 19publications
- 6journal articles
- 11conference papers
- 320+citations
- 9h-index
- 5Q1 journals
- 2best-paper awards
Counts from Google Scholar · see the live profile for current counts.
Doctoral thesis
Neuro-Symbolic Architectures for Natural Language Comprehension
My doctoral research developed neuro-symbolic architectures for natural language comprehension, pairing neural models with symbolic structure, and applied them to real problems across energy, healthcare and finance. The work produced publications in Q1 journals and two best-paper awards.
Journal articles
6Generative AI Agents for Bedside Sleep Apnea Detection and Sleep Coaching
Addressing the Information Asymmetry of Fake News Detection Using Large Language Models and Emotion Embeddings
Emotion AWARE: an artificial intelligence framework for adaptable, robust, explainable, and multi-granular emotion analysis
A self structuring artificial intelligence framework for deep emotions modeling and analysis on the social web
A Crowdsourced Gameplay for Whole-Genome Assembly via Short Reads
Phylogenetic Tree Construction Using k-mer Forest-Based Distance Calculation
Conference papers
11Generative AI and EEG-based Music Personalization for Work Stress Reduction
Multi-Agent RAG Chatbot Architecture for Decision Support in Net-Zero Emission Energy Systems
EmoZen: A Robust Word Embedding for Implicit and Explicit Expressions of Emotion
Augmenting Industrial Chatbots in Energy Systems using ChatGPT Generative AI
An Artificial Intelligence Framework for the Detection of Emotion Transitions in Telehealth Services
Best paper
A BERT-based Idiom Detection Model
Cooee: An Artificial Intelligence Chatbot for Complex Energy Environments
Investigating COVID-19 Vaccine Messaging in Online Social Networks using Artificial Intelligence
UNISOLAR: An Open Dataset of Photovoltaic Solar Energy Generation in a Large Multi-Campus University Setting
Alignment-free Whole Genome Comparison Using k-mer Forests
Best paper
Reinstating Dlib Correlation Human Trackers Under Occlusions in Human Detection based Tracking
Preprints & abstracts
2Emotional transformations during Victoria's Cancer Council 131120 information and support service calls detected using Artificial Intelligence
Exploratory Analysis of a Social Media Network in Sri Lanka during the COVID-19 Virus Outbreak
Achievements
Best Paper Award
15th IEEE International Conference on Human System Interaction (HSI), Melbourne, Australia
For "An Artificial Intelligence Framework for the Detection of Emotion Transitions in Telehealth Services".
Best Paper Award
19th International Conference on Advances in ICT for Emerging Regions (ICTer), Colombo, Sri Lanka
For "Alignment-free Whole Genome Comparison Using k-mer Forests", one of 22 accepted from 110 submissions.
Centre for Data Analytics and Cognition (CDAC) Scholarship
La Trobe University
Doctoral research scholarship from the university’s Centre for Data Analytics and Cognition.
La Trobe University Full-Fee Research Scholarship (LTUFFRS)
La Trobe University
Full-fee doctoral research scholarship.
TEFMA Clever Campus Innovation Award
Tertiary Education Facilities Management Association
For the La Trobe Energy Analytics Platform (LEAP), the live data space behind the Cooee chatbot.
Postgraduate Travel Grant
La Trobe Business School
For international conference participation as a doctoral student.
Overall Champions, HackLN 2k17 Inter-University Hackathon
Department of Statistics and Computer Science, University of Kelaniya, Sri Lanka
An IoT child-safety module for bicycles with a companion Android app: proximity and fall detection, real-time location tracking, and a one-tap call to a parent.
Dean's List Honours
University of Moratuwa, Sri Lanka
Dean’s List Honours in every semester of the B.Sc. (Hons) Computer Science and Engineering program, for maintaining a GPA above 3.8.